Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d33ad4c1a79e925012aa3648e48a8968067579d9687ecf48f6023185629ad94
+oid sha256:6f03a358d955ba4ce6a44c394dbe7413af796f396d3152332949dcc82a6ef42f
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ace5899b79786586af39fa76466bed466a00679c61f636c0ea585ccf64f5c9e
-size 91850362
+oid sha256:703122132b31ba1496b69159164e8768b24d25fb4e1a8e94f36810752e3dfd2b
+size 91850618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ae149e690485daeea42c52c1efd7cb49776e5b2c602981e16e02930c454313
+oid sha256:77999305cec94140e654fc55c9e5ee491f25ef66d67c59f300d5c548a1478dba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5245962b37abe5debb29d3c0771306ab720257c32ca897672f6c78751ec6642f
+oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.482667922973633,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.04131548504379441,
+  "best_metric": 2.4008781909942627,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.0495785820525533,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 58.361,
       "eval_steps_per_second": 14.59,
       "step": 250
+    },
+    {
+      "epoch": 0.04296810444554619,
+      "grad_norm": 2.223804473876953,
+      "learning_rate": 0.00012039360249617425,
+      "loss": 2.3776,
+      "step": 260
+    },
+    {
+      "epoch": 0.04462072384729797,
+      "grad_norm": 2.835205078125,
+      "learning_rate": 0.00011280404514057264,
+      "loss": 2.2912,
+      "step": 270
+    },
+    {
+      "epoch": 0.04627334324904974,
+      "grad_norm": 4.878274917602539,
+      "learning_rate": 0.00010519595485942743,
+      "loss": 2.1857,
+      "step": 280
+    },
+    {
+      "epoch": 0.04792596265080152,
+      "grad_norm": 5.728613376617432,
+      "learning_rate": 9.76063975038258e-05,
+      "loss": 2.2346,
+      "step": 290
+    },
+    {
+      "epoch": 0.0495785820525533,
+      "grad_norm": 16.714305877685547,
+      "learning_rate": 9.00723486343046e-05,
+      "loss": 2.2206,
+      "step": 300
+    },
+    {
+      "epoch": 0.0495785820525533,
+      "eval_loss": 2.4008781909942627,
+      "eval_runtime": 43.6638,
+      "eval_samples_per_second": 58.355,
+      "eval_steps_per_second": 14.589,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6293571313336320.0,
+  "total_flos": 7557290404085760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null